INDEX

Explanations

words and phrases expressing negation or absence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"Not" followed by limiting adverbs

np_acts-logits-general · gemini-2.0-flash

not only

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 não

-0.60

cuid

-0.49

hic

-0.49

هما

-0.46

 Tweed

-0.46

 pymongo

-0.46

nasa

-0.45

 Planeta

-0.45

El

-0.45

POSITIVE LOGITS

 necessarily

1.18

yet

1.16

yet

1.05

ValueStyle

0.98

Yet

0.95

Yet

0.94

necessarily

0.94

YET

0.93

 hề

0.91

ьаж

0.90

Activations Density 0.404%

words and phrases expressing negation or absence

"Not" followed by limiting adverbs

not only

No Comments

No Known Activations